Abstract: The technologies described herein are generally directed to launching radio spectrum resources in a fifth generation (5G) network or other next generation networks. For example, a method described herein can include, confirming, by site launching equipment, installation of components of a base station, resulting in a confirmed installation. The method can further comprise, based on the confirmed installation, facilitating, by the site launching equipment, integrating the base station into a communications network. Further, in response to the integrating, launching, by the site launching equipment, operation of the base station for a testing of performance of the base station, the testing resulting in a tested base station. The method can further comprise activating, by the site launching equipment, the tested base station for use by authorized user equipment via the communications network.

Abstract: A processing system may obtain values of carrier attributes for a new carrier to be deployed in a cellular network, obtain values of the carrier attributes and values of a configuration parameter for a plurality of existing carriers in the cellular network, and construct an attribute value matrix comprising the values of the carrier attributes for the plurality of existing carriers, where the attribute value matrix associates the carrier attributes to the plurality of existing carriers, apply a regression to a function associating the attribute value matrix to a vector of the values of the configuration parameter for the plurality of existing carriers to learn coefficients of the function, apply the coefficients to a vector comprising the values of the plurality of carrier attributes for the new carrier to generate a value of the configuration parameter for the new carrier, and apply the generated value to the new carrier.

Abstract: A method, system and computer-readable medium where a weighted composite quality index having a plurality of components for a network element is identified. A historical baseline value from historical data for each component is determined, and a deviation from the historical baseline values is measured. A risk level for the deviation is assigned. A loss score for the measured components is computed by mapping the risk level to a numerical score. An aggregated risk score based on a sum of weighted risk scores for each of the components is computed. An expected risk score based on probabilities associated with the aggregated risk score is determined by computing future probabilities of each risk level at the network element based on a trained machine learning model.

Abstract: A processing system may obtain values of carrier attributes for a new carrier to be deployed in a cellular network, obtain values of the carrier attributes and values of a configuration parameter for a plurality of existing carriers in the cellular network, and construct an attribute value matrix comprising the values of the carrier attributes for the plurality of existing carriers, where the attribute value matrix associates the carrier attributes to the plurality of existing carriers, apply a regression to a function associating the attribute value matrix to a vector of the values of the configuration parameter for the plurality of existing carriers to learn coefficients of the function, apply the coefficients to a vector comprising the values of the plurality of carrier attributes for the new carrier to generate a value of the configuration parameter for the new carrier, and apply the generated value to the new carrier.

Abstract: A method, system and computer-readable medium where a weighted composite quality index having a plurality of components for a network element is identified. A historical baseline value from historical data for each component is determined, and a deviation from the historical baseline values is measured. A risk level for the deviation is assigned. A loss score for the measured components is computed by mapping the risk level to a numerical score. An aggregated risk score based on a sum of weighted risk scores for each of the components is computed. An expected risk score based on probabilities associated with the aggregated risk score is determined by computing future probabilities of each risk level at the network element based on a trained machine learning model.

Abstract: A method, system and computer-readable medium where a weighted composite quality index having a plurality of components for a network element is identified. A historical baseline value from historical data for each component is determined, and a deviation from the historical baseline values is measured. A risk level for the deviation is assigned. A loss score for the measured components is computed by mapping the risk level to a numerical score. An aggregated risk score based on a sum of weighted risk scores for each of the components is computed. An expected risk score based on probabilities associated with the aggregated risk score is determined by computing future probabilities of each risk level at the network element based on a trained machine learning model.